KR20230117404A - Medical image processing apparatus, medical image processing method, computer readable storage medium, and radiation therapy apparatus - Google Patents

Abstract

The medical image processing device of the embodiment includes a first image acquisition unit, a second image acquisition unit, a first likelihood distribution calculation unit, a tracking availability determining unit, and a tracking unit. The first image acquisition unit acquires a first image that is a perspective image of the patient. The second image acquisition unit acquires a second image, which is a perspective image of the patient, generated at a time different from that of the first image. The first likelihood distribution calculator calculates a first likelihood distribution indicating a distribution of likelihoods representing object features in the first image. The tracking availability determining unit determines whether tracking of the object is possible based on the first likelihood distribution. The tracking unit tracks the position of the object in the second image according to the determination result.

Description

Medical image processing apparatus, medical image processing method, medical image processing program, and radiation therapy apparatus

Embodiments of the present invention relate to a medical image processing apparatus, a medical image processing method, a medical image processing program, and a radiation treatment apparatus.

Radiation therapy is a treatment method in which radiation is irradiated to a lesion in a patient's body to destroy the lesion. At this time, radiation needs to be accurately irradiated to the location of the lesion. This is because irradiation of radiation to a normal tissue in a patient's body may have an effect on the normal tissue as well. For this reason, when performing radiation therapy, first, in the stage of treatment planning, computed tomography (CT) is performed in advance, and the position of the lesion in the patient's body is grasped three-dimensionally. Then, based on the grasped position of the lesion, the radiation direction and radiation intensity are planned so as to reduce radiation to normal tissues. After that, in the treatment stage, the position of the patient is aligned with the patient's position in the treatment planning stage, and radiation is irradiated to the lesion according to the irradiation direction and irradiation intensity planned in the treatment planning stage.

In the position alignment of the patient in the treatment stage, three-dimensional CT data is virtually arranged in the treatment room, and the position of the patient lying on the movable bed in the treatment room coincides with the position of the three-dimensional CT data. Adjust the More specifically, a digitally reconstructed X-ray image (digitally By collating two images of Reconstructed Radiograph (DRR) images, the displacement of the patient's position between the respective images is obtained. Then, based on the discrepancy of the patient's position obtained by image collation, the bed is moved to align the positions of lesions, bones, etc. in the patient's body with those at the time of treatment planning. Thereafter, radiation is irradiated to the lesion while comparing the X-ray fluoroscopy image and the DRR image taken again.

When the patient's lesion is located in an organ that moves due to respiration or heartbeat movement, such as the lungs and liver, it is necessary to specify the position of the lesion under investigation. For example, the position of the lesion can be tracked by taking an X-ray fluoroscopic image of a patient being irradiated with radiation. In the case where the lesion is not clearly captured in the X-ray fluoroscopic image, the position of the lesion can be indirectly tracked by tracking the marker located in the patient's body. As a method of irradiating radiation, there is a follow-up irradiation in which radiation is irradiated while following the location of a lesion, and an ambush irradiation in which radiation is irradiated when a lesion is located at a location at the time of treatment planning. Such an investigation method is called a respiratory motive investigation method.

However, for example, when an object such as a lesion or marker overlaps an organ such as the liver with low X-ray transmittance, the lesion or marker may not be clearly captured in an X-ray fluoroscopic image. Also, in the X-ray fluoroscopic image, there may be a pattern that is difficult to distinguish from a marker, such as a rib. In this case, there is a possibility that the position of an object such as a lesion or a marker cannot be tracked.

Japanese Unexamined Patent Publication No. 2018-82767

An object to be solved by the present invention is to provide a medical image processing apparatus, a medical image processing method, a medical image processing program, and a radiation treatment apparatus capable of tracking an object inside a patient's body with high precision from a perspective image of the patient.

A medical image processing device according to an embodiment is a device for tracking the position of an object inside a patient's body, and includes: a first image acquisition unit, a second image acquisition unit, a first likelihood distribution calculation unit, a tracking availability determination unit; have a tracer The first image acquisition unit acquires a plurality of first images of different photographing directions as perspective images of the patient. The second image acquisition unit acquires a plurality of second images in different photographing directions as perspective images of the patient generated at different times from the first image. The first likelihood distribution calculator calculates a first likelihood distribution representing a likelihood distribution representing the object feature in each of the plurality of first images acquired by the first image acquisition unit. The tracking availability determining unit determines whether tracking of the object is possible based on the first likelihood distribution calculated by the first likelihood distribution calculating unit. The tracking unit tracks the position of the object in the second image acquired by the second image acquisition unit according to the determination result of the tracking permission determination unit.

1 is a block diagram showing a schematic configuration of a treatment system according to a first embodiment;
Fig. 2 is a block diagram showing a schematic configuration of a medical image processing apparatus according to the first embodiment.
Fig. 3 is a diagram showing an example of a first image according to the first embodiment;
Fig. 4 is a diagram showing an example of a template used for calculating the degree of separation according to the first embodiment;
Fig. 5 is a flowchart showing the operation of the medical image processing apparatus in the previous stage of treating a patient according to the first embodiment.
Fig. 6 is a flowchart showing the operation of the medical image processing apparatus during treatment of a patient according to the first embodiment;
Fig. 7 is a block diagram showing a schematic configuration of a medical image processing apparatus according to a second embodiment.
Fig. 8 is a flowchart showing the operation of the medical image processing apparatus in the previous stage of treating a patient according to the second embodiment.
9 is a block diagram showing a schematic configuration of a radiation treatment apparatus according to a third embodiment.
Fig. 10 is a flowchart showing the operation of the radiation treatment apparatus during treatment of a patient according to the third embodiment.

Hereinafter, a medical image processing apparatus, a medical image processing method, a medical image processing program, and a radiation treatment apparatus according to embodiments will be described with reference to the drawings.

(First Embodiment)

1 is a block diagram showing a schematic configuration of a treatment system according to a first embodiment. The treatment system 1 includes, for example, a treatment table 10, a bed control unit 11, two radiation sources 20 (radiation sources 20-1 and radiation sources 20-2), and two radiation sources. Detectors 30 (radiation detector 30-1 and radiation detector 30-2), a treatment beam irradiation door 40, an irradiation control device 50, and a medical image processing device 100 are provided. .

In addition, "-" given next to each symbol shown in FIG. 1 and the number following it are for identifying correspondence. More specifically, the correspondence relationship between the radiation source 20 and the radiation detector 30 indicates that the radiation source 20-1 and the radiation detector 30-1 correspond to each other and form a pair, and the radiation source 20-2 ) and the radiation detector 30-2 correspond to each other and form another set. In addition, in the following description, when displaying a plurality of identical components without distinguishing them, "-" and the number following them are displayed without showing them.

The treatment table 10 is a bed for fixing a subject (patient) P undergoing radiation treatment. The bed controller 11 is a controller that controls a translation mechanism and a rotation mechanism provided on the treatment table 10 to change the irradiation direction of the treatment beam B to the patient P fixed on the treatment table 10 . The bed controller 11 controls each of the translation mechanism and the rotation mechanism of the treatment table 10 in the 3-axis direction, that is, in the 6-axis direction, for example.

The radiation source 20-1 emits radiation r-1 for projecting the inside of the patient P from a predetermined angle. The radiation source 20-2 emits radiation r-2 for projecting the body of the patient P from a predetermined angle different from that of the radiation source 20-1. Radiation r-1 and radiation r-2 are, for example, X-rays. FIG. 1 shows a case where X-ray imaging is performed from two directions with respect to the patient P fixed on the treatment table 10 . In addition, in FIG. 1, illustration of the control part which controls irradiation of the radiation r by the radiation source 20 is abbreviate|omitted.

The radiation detector 30-1 detects the radiation r-1 that has been irradiated from the radiation source 20-1 and has passed through the body of the patient P and reaches the patient P according to the magnitude of the energy of the detected radiation r-1. Creates an X-ray fluoroscopic image of the body. The radiation detector 30-2 detects the radiation r-2 that has been irradiated from the radiation source 20-2 and has passed through the patient P's body and has reached the patient P's radiation level according to the magnitude of the energy of the detected radiation r-2. Creates an X-ray fluoroscopic image of the body.

In the radiation detector 30, X-ray detectors are arranged in a two-dimensional array, and a digital image representing the magnitude of the energy of radiation r reaching each X-ray detector as a digital value is generated as an X-ray perspective image. . The radiation detector 30 is, for example, a flat panel detector (FPD), an image intensifier, or a color image intensifier. In the following description, it is assumed that each radiation detector 30 is an FPD. The radiation detector 30 (FPD) outputs each generated X-ray perspective image to the medical image processing apparatus 100 . In FIG. 1, illustration of a control unit that controls generation of an X-ray perspective image by the radiation detector 30 is omitted.

In addition, in FIG. 1, the structure of the treatment system 1 provided with two imaging devices (a set of the radiation source 20 and the radiation detector 30) is shown. However, the number of imaging devices included in the treatment system 1 is not limited to two. For example, the treatment system 1 may include three or more imaging devices (three or more sets of radiation sources 20 and radiation detectors 30).

The treatment beam irradiation door 40 irradiates, as a treatment beam B, radiation for destroying lesions in the body of the patient P. The treatment beam B is, for example, an X-ray, a γ-ray, an electron beam, a proton beam, a neutron beam, or a heavy particle beam. The treatment beam B is irradiated to the patient P (more specifically, to the lesion in the body of the patient P) in a straight line from the treatment beam irradiation door 40 .

The irradiation control device 50 controls irradiation of the treatment beam B by the treatment beam irradiation door 40 . The irradiation control device 50 irradiates the patient P with the treatment beam B from the treatment beam irradiation door 40 according to the irradiation instruction signal indicating the irradiation timing of the treatment beam B output from the medical image processing device 100. .

In FIG. 1, the configuration of the treatment system 1 having one fixed treatment beam irradiation door 40 is shown, but is not limited thereto, and the treatment system 1 includes a plurality of treatment beam irradiation doors. may be provided For example, the treatment system 1 may further include a treatment beam irradiation door for irradiating the patient P with a treatment beam from a horizontal direction. Further, the treatment system 1 may have a configuration in which one treatment beam irradiation gate rotates around the patient P to irradiate the patient P with treatment beams from multiple directions. More specifically, the treatment beam irradiation door 40 shown in FIG. 1 may be configured to rotate 360 degrees about the rotation axis in the horizontal direction Y shown in FIG. 1 . The treatment system 1 of this configuration is called a rotary gantry type treatment system. Further, in the rotary gantry type treatment system, the radiation source 20 and the radiation detector 30 simultaneously rotate 360 degrees about the same axis as the rotation axis of the treatment beam irradiation door 40 .

The medical image processing apparatus 100 tracks the position of an object in the patient P's body that moves due to the movement of the patient P's respiration or heartbeat, such as the lungs and liver, and irradiates the treatment beam B to the lesion of the patient P. decide The object inside the body of patient P is a metal marker placed inside the body of patient P, but is not limited thereto. For example, the object inside the body of patient P may be a lesion inside the body of patient P. In the following description, an example in which the object is a marker will be described.

The medical image processing apparatus 100 determines the irradiation timing of the treatment beam B to be irradiated onto the lesion by tracking the marker image in the X-ray fluoroscopic image of the patient P taken in real time by each radiation detector 30. automatically decide At this time, the medical image processing apparatus 100 determines whether the position of the image of the marker placed in the body of the patient P being tracked is within a predetermined range for performing radiation treatment. Then, the medical image processing device 100 outputs an irradiation instruction signal instructing irradiation of the treatment beam B to the irradiation control device 50 when the position of the marker image is within a predetermined range. Thus, the irradiation control device 50 irradiates the treatment beam irradiation door 40 with the treatment beam B according to the irradiation instruction signal output from the medical image processing device 100 .

In addition, the medical image processing apparatus 100 performs image processing for positioning to align the current position of the patient P with a predetermined position in a planning stage before radiation treatment, such as a treatment planning stage. The medical image processing apparatus 100 includes a DRR image obtained by virtually reconstructing an X-ray fluoroscopy image from a three-dimensional CT image or the like taken before radiation treatment, and a DRR image output by each radiation detector 30. By collating the current X-ray fluoroscopy image, the position of the patient P suitable for performing radiation treatment is automatically searched for. Then, the medical image processing apparatus 100 determines the amount of movement of the treatment table 10 for moving the current position of the patient P fixed on the treatment table 10 to a predetermined suitable position for performing radiation treatment. save Details regarding the configuration and processing of the medical image processing apparatus 100 will be described later.

Further, each of the medical image processing apparatus 100 and the radiation detector 30 may be connected by a LAN (Local Area Network) or a WAN (Wide Area Network).

Next, the configuration of the medical image processing apparatus 100 constituting the treatment system 1 will be described. Fig. 2 is a block diagram showing a schematic configuration of the medical image processing apparatus according to the first embodiment. The medical image processing apparatus 100 shown in FIG. 2 includes a first image acquisition unit 101, a first likelihood distribution calculation unit 102, a tracking availability determination unit 103, a tracking unit 104, A second image acquiring unit 105 and a second likelihood distribution calculating unit 106 are provided.

The first image acquisition unit 101 acquires a plurality of first images of different shooting directions as perspective images of the patient P. The first image may be an X-ray fluoroscopy image captured by the radiation detector 30 in determining the position of the patient P described above, or a 3D CT image or the like taken in advance before performing radiation therapy to virtually X-ray. It may be a DRR image reconstructed from a line perspective image.

The first likelihood distribution calculation unit 102 indicates a distribution of likelihoods representing marker (object) features in each of a plurality of first images 60 acquired by the first image acquisition unit 101. Calculate the first likelihood distribution.

3 is a diagram showing an example of a first image according to the first embodiment. The first image 60 includes an image of the marker 62 placed inside the body of patient P and an image of the lesion 63 inside the body of patient P. The first likelihood distribution calculator 102 does not calculate the likelihood distribution for the entire first image 60, but calculates the likelihood distribution for the tracking area 61. The tracking area 61 is an area for tracking the position of the marker 62, and is an area including a range in which the marker 62 moves due to movement of the patient P's respiration or heartbeat. In this way, by limiting the target for calculating the first likelihood distribution to a part (tracking area 61) in the first image 60, the processing load of the first likelihood distribution calculator 102 can be reduced. .

For example, the tracking area 61 is determined based on the position of the marker 62 designated on the CT image during treatment planning. Further, the tracking area 61 is determined in consideration of a margin based on an error that may occur during actual treatment. For example, the tracking area 61 may be an area projected on the first image by a three-dimensional area with a margin added centering on the position of the marker 62 on the CT image. Further, the tracking area 61 may be determined according to a margin determined in consideration of the condition of the patient immediately before treatment.

In Fig. 3, the marker 62 is a bar-shaped marker, but the shape of the marker 62 is not limited to this. For example, a spherical marker may be used.

Next, the likelihood calculation method by the first likelihood distribution calculator 102 will be described. The first likelihood distribution calculator 102 calculates the likelihood by preserving the image pattern when the marker 62 is projected as a template image and calculating the degree of similarity between the first image 60 and the template image.

When the shape of the shadow of the marker 62 can be predicted in advance, such as when the marker 62 is spherical, an image in which the shadow is drawn may be used as a template image. In addition, when the shadow of the marker 62 changes according to the posture of the marker 62 when it is placed in the body of the patient P, a plurality of template images in which the shadow according to the posture of the marker 62 is drawn are generated. , one of a plurality of template images may be selected and used.

The degree of similarity, which is a numerical value of likelihood, is expressed by pixel values or spatial correlation values between the template image and the first image 60 . For example, the degree of similarity may be the reciprocal of the difference between pixel values at each corresponding pixel position. Further, the degree of similarity may be a cross-correlation value of a corresponding pixel position.

Alternatively, the first likelihood distribution calculator 102 may generate an identifier by a machine learning method using the template image including the marker 62 as learning data, and calculate a likelihood using the generated identifier. For example, an identifier is generated by preparing a plurality of template images in which the markers 62 are included and first images 60 in positions where the markers 62 are not included, and learning these by a machine learning method. By using the generated identifier, it is possible to identify whether the marker 62 is included or not.

In addition, as a machine learning method, you may use a support vector machine, a random forest, or deep learning. The first likelihood distribution calculation unit 102 calculates a real value calculated using such a machine learning method as a likelihood. As the actual numerical value, for example, the distance to the identification boundary, the ratio of the discriminator determined to contain the object, or the output value of Softmax may be used.

Also, the first likelihood distribution calculator 102 may calculate the likelihood using the degree of separation. 4 is a diagram showing an example of a template used for calculating the degree of separation according to the first embodiment. In one example of the template 70 shown in FIG. 4 , the first area 71 where the bar-shaped marker 62 exists and the second area 72 other than the first area 71 are classified. That is, the second area 72 is an area where the rod-shaped marker 62 does not exist.

In the calculation of the degree of separation, when a region similar to that of the template 70 exists in the first image 60, the histogram of pixel values included in the first image 60 indicates the pixel values belonging to the first region 71. It is classified into each of a histogram of and a histogram of pixel values belonging to the second region 72 . This is because, when the image of the marker 62 printed on the first image 60 overlaps the first area 71, the histogram of pixel values belonging to the first area 71 has a high frequency of pixel values of dark pixels, This is because the histogram of pixel values belonging to the second area 72 has a high frequency of pixel values of bright pixels.

The first likelihood distribution calculation unit 102 quantifies the histogram separability of pixel values as described above using Fisher's criterion. Then, the first likelihood distribution calculation unit 102 calculates the ratio of the mean of pixel value variances of pixels belonging to each region (intra-class variance) to the variance of pixel values between each region (inter-class variance). is calculated, and this ratio is calculated as the degree of separation. In this way, the first likelihood distribution calculator 102 calculates the degree of separation calculated using the template 70 as the likelihood. The first likelihood distribution calculation unit 102 uses the calculated likelihood to display a distribution of likelihoods in each of a plurality of first images 60 acquired by the first image acquisition unit 101. Calculate the likelihood distribution.

The tracking availability determining unit 103 determines whether the tracking of the marker 62 is enabled based on the first likelihood distribution calculated by the first likelihood distribution calculating unit 102 . Specifically, the tracking availability determining unit 103 calculates the difficulty of tracking the first image 60 in each shooting direction based on the first likelihood distribution calculated by the first likelihood distribution calculating unit 102 do. Further, the tracking enable/disable determination unit 103 determines that tracking of the marker 62 is impossible when the tracking difficulty is higher than a predetermined threshold value.

The tracking availability determining unit 103 calculates the tracking difficulty based on the statistic of the first likelihood distribution. The statistic is, for example, a first-order statistic such as an average value of the first likelihood distribution and a variance of the first likelihood distribution, but is not limited thereto. For example, the statistic may be the maximum value of the first likelihood distribution, or may be a value calculated by a linear expression incorporating these numerical values. In addition, when the position of the marker 62 corresponding to the first likelihood distribution is obtained, the tracking availability determination unit 103 narrows down the tracking difficulty to the statistic of the first likelihood distribution in the periphery of the position of the marker 62 can be calculated. The tracking availability determination unit 103 outputs the determination result of the tracking of the marker 62 for each photographing direction to the tracking unit 104 and the second image acquisition unit 105 .

The tracking unit 104 tracks the position of the marker 62 in the second image acquired by the second image acquisition unit 105 according to the determination result of the tracking availability determination unit 103 . Details of the tracking process by the tracking unit 104 will be described later.

The second image acquisition unit 105 acquires a plurality of second images in different photographing directions as perspective images of the patient P generated at different times from the first image. The above-described first image is a perspective image generated based on a three-dimensional image of patient P taken during treatment planning, or a perspective image taken from the same shooting direction as the second image immediately before treatment, but the second image, It is a fluoroscopic image taken by the radiation detector 30 during treatment for patient P. To track the marker 62, second images are repeatedly taken at predetermined time intervals.

The shooting direction of the first image is preferably the same as that of the second image. For example, when the second image is captured from a direction different from when the patient P is positioned, the first image is not a perspective image captured when the patient P is positioned, but is captured from the same direction as the second image. It may be a DRR image simulating a perspective image. Further, the first image may be a second image taken during the previous treatment or may be an image taken from the same direction as the second image immediately before the treatment. Also, the first image may be a moving image of one or more breathing cycles.

In addition, the second image acquisition unit 105, before treatment by irradiation of the treatment beam B is performed on the patient P, based on the determination result of the tracking enable/disable judgment unit 103, the tracking unit 104 The shooting direction of the second image used for tracking the position of the marker 62 is determined. For example, the determination result for the first image in the imaging direction of the radiation detector 30-1 is "trackable", and the determination result for the first image in the imaging direction of the radiation detector 30-2 is "tracking possible" possible”, the second image acquisition unit 105 acquires both the second image captured by the radiation detector 30-1 and the second image captured by the radiation detector 30-2. In addition, the determination result for the first image in the imaging direction of the radiation detector 30-1 is "trackable", and the determination result for the first image in the imaging direction of the radiation detector 30-2 is "tracking impossible" In this case, the second image acquisition unit 105 acquires only the second image captured by the radiation detector 30-1. Further, the determination result for the first image in the imaging direction of the radiation detector 30-1 is "unable to track", and the judgment result for the first image in the imaging direction of the radiation detector 30-2 is "trackable". In this case, the second image acquisition unit 105 acquires only the second image captured by the radiation detector 30-2.

In this way, the second image acquisition unit 105 does not acquire the second image in the shooting direction in which it is determined that the marker 62 cannot be tracked, thereby suppressing the radiation exposure of the patient P, The success rate of tracking the marker 62 can be improved.

The second likelihood distribution calculation unit 106 calculates a second likelihood distribution representing a likelihood distribution in the second image acquired by the second image acquiring unit 105 . Here, the second likelihood distribution calculator 106 does not calculate the second likelihood distribution for the entire second image, but calculates the second likelihood distribution for the tracking area 61 in the second image. Since the calculation method of the second likelihood distribution is the same as the calculation method of the first likelihood distribution, description thereof is omitted.

The tracking unit 104 determines the position of the marker 62 in the second image based on the second likelihood distribution calculated by the second likelihood distribution calculating unit 106 . For example, the tracking unit 104 determines that the position of the maximum value in the second likelihood distribution is the position of the marker 62 .

When the second image is acquired from two directions, if the position of the marker 62 in one second image is specified, the position of the marker 62 in the other second image is geometrically epipolar limited on the line. Therefore, in the second likelihood distribution of the other second image, the tracking unit 104 may determine that the position of the maximum value in the likelihood distribution on the epipolar line is the position of the marker 62 . When the second image is acquired from two directions, the tracking unit 104 may geometrically transform and calculate the position of the marker 62 into three-dimensional coordinates.

The tracking unit 104 determines the irradiation timing of the treatment beam B based on the determined position of the marker 62 . The positional relationship between the marker 62 and the lesion 63 can be specified from a fluoroscopic image of patient P obtained during treatment planning. For this reason, the tracking unit 104 instructs irradiation of the treatment beam B when the position of the lesion 63 in the body of the patient P, which is specified based on the position of the marker 62, is located within a predetermined range. An irradiation instruction signal is transmitted to the irradiation control device 50 .

The irradiation control device 50 irradiates the treatment beam B from the treatment beam irradiation door 40 according to the irradiation instruction signal received from the medical image processing device 100 . In this way, the treatment beam B can be irradiated to the lesion 63 in the body of the patient P.

On the other hand, the tracking unit 104 sends an irradiation instruction signal to the irradiation control device ( 50) is not transmitted. In this way, irradiation of the treatment beam B to areas other than the lesion 63 can be suppressed.

In addition, some or all of the functions of components included in the above-described medical image processing apparatus 100 may include, for example, a hardware processor such as a CPU (Central Processing Unit) and a storage device (non-software) storing programs (software). A storage device having a temporary storage medium) may be provided, and various functions may be realized by a processor executing a program. In addition, some or all of the functions of components provided in the above-described medical image processing apparatus 100 may include a large scale integration (LSI), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a GPU ( Graphics Processing Unit) or other hardware (circuit section; including circuitry), etc., or various functions may be realized by cooperation between software and hardware. In addition, some or all of the functions of components included in the above-described medical image processing apparatus 100 may be implemented by a dedicated LSI.

Here, the program (software) is a storage device (non-transitory storage medium) provided in the treatment system 1 in advance, such as ROM (Read Only Memory), RAM (Random Access Memory), HDD (Hard Disk Drive), flash memory, etc. It may be stored in a storage device), or it may be stored in a removable storage medium (non-transitory storage medium) such as a DVD or CD-ROM, and the storage medium is mounted on a drive unit provided in the treatment system 1. By doing so, it may be installed in the storage device provided in the treatment system 1. In addition, the program (software) may be downloaded in advance via a network from another computer device and installed in the storage device provided in the treatment system 1.

5 is a flowchart showing the operation of the medical image processing apparatus in the previous stage of treating a patient according to the first embodiment. The process according to this flowchart is executed by the medical image processing apparatus 100 in a step prior to the treatment by irradiation of the treatment beam B on the patient P.

First, the first image acquiring unit 101 acquires a plurality of first images of different shooting directions as perspective images of patient P (S101). As described above, the first image may be an X-ray fluoroscopy image taken by the radiation detector 30 when positioning the patient P, or a three-dimensional CT image taken in advance before performing radiation treatment. It may be a DRR image obtained by virtually reconstructing an X-ray fluoroscopy image.

Next, the first likelihood distribution calculation unit 102 calculates the likelihood of displaying marker (object) characteristics in each of the plurality of first images 60 acquired by the first image acquisition unit 101. A first likelihood distribution representing the distribution is calculated (S102). Here, the first likelihood distribution calculating unit 102 does not calculate the likelihood distribution in the entire first image 60, but rather in the tracking area 61 shown in FIG. 3.

Next, based on the first likelihood distribution calculated by the first likelihood distribution calculation unit 102, the tracking availability determining unit 103 determines whether tracking of the marker 62 is possible (S103). For example, based on the first likelihood distribution calculated by the first likelihood distribution calculation unit 102, the tracking availability determining unit 103 determines the difficulty of tracking the first image 60 in each shooting direction. yield Further, the tracking enable/disable determination unit 103 determines that tracking of the marker 62 is impossible when the tracking difficulty is higher than a predetermined threshold value.

After that, the second image acquisition unit 105 determines the shooting direction of the second image based on the determination result of the tracking enable/disable judgment unit 103 (S104), and ends the process according to this flowchart. In addition, when treatment by irradiation of the treatment beam B is performed on the patient P, tracking of the marker 62 is performed based on the second image corresponding to the imaging direction determined in step S104.

6 is a flowchart showing the operation of the medical image processing apparatus during treatment of a patient according to the first embodiment. The processing according to this flowchart is repeatedly executed at predetermined time intervals by the medical image processing apparatus 100 in the step of performing treatment by irradiation of the treatment beam B on the patient P.

First, the second image acquisition unit 105 acquires a second image corresponding to the shooting direction determined in step S104 (S201). The second image is an image captured by the radiation detector 30 during treatment for patient P. Specifically, the second image acquisition unit 105 does not acquire a second image for a shooting direction in which the tracking difficulty is higher than the predetermined threshold, and acquires only the second image in which the tracking difficulty is equal to or less than the predetermined threshold.

Next, the second likelihood distribution calculation unit 106 calculates a second likelihood distribution indicating the likelihood distribution in the second image acquired by the second image acquisition unit 105 (S202). The calculation method of the second likelihood distribution is the same as the calculation method of the first likelihood distribution.

Next, the tracking unit 104 determines the position of the marker 62 (object) in the second image based on the second likelihood distribution calculated by the second likelihood distribution calculating unit 106 ( S203). For example, the tracking unit 104 determines that the position of the maximum value in the second likelihood distribution is the position of the marker 62 .

After that, the tracking unit 104 determines the irradiation timing of the treatment beam B based on the determined position of the marker 62 (object) (S204). For example, the tracking unit 104 instructs irradiation of the treatment beam B when the position of the lesion 63 in the body of the patient P, which is specified based on the position of the marker 62, is within a predetermined range. and transmits an irradiation instruction signal to the irradiation control device 50. The irradiation control device 50 irradiates the treatment beam B from the treatment beam irradiation door 40 according to the irradiation instruction signal received from the medical image processing device 100 .

As described above, in the first embodiment, the first image acquisition unit 101 acquires a plurality of first images of different shooting directions as perspective images of the patient P. The second image acquisition unit 105 acquires a plurality of second images in different photographing directions as perspective images of the patient P generated at different times from the first image. The first likelihood distribution calculation unit 102 calculates a first likelihood distribution representing a likelihood distribution representing object characteristics in each of a plurality of first images acquired by the first image acquisition unit 101. do. The tracking availability determining unit 103 determines whether tracking of the object is possible based on the first likelihood distribution calculated by the first likelihood distribution calculating unit 102 . The tracking unit 104 tracks the position of the object in the second image acquired by the second image acquisition unit 105 according to the determination result of the tracking availability determination unit 103 . This makes it possible to track objects inside the patient's body with high precision from the patient's perspective image.

(Second Embodiment)

In the first embodiment, the second image acquisition unit 105 decides the shooting direction of the second image based on the determination result of the tracking permission determination unit 103. In contrast, in the second embodiment, the tracking unit 104 determines a tracking area, which is an area in which the position of an object is tracked, based on the determination result of the tracking permission determining unit 103. In this way, objects inside the patient's body can be tracked with higher precision. Hereinafter, the second embodiment will be described in detail.

Fig. 7 is a block diagram showing a schematic configuration of a medical image processing apparatus according to a second embodiment. In Fig. 7, the same reference numerals are assigned to parts corresponding to the respective parts in Fig. 2, and descriptions thereof are omitted.

The tracking availability determining unit 103 determines whether the tracking of the marker 62 is enabled based on the first likelihood distribution calculated by the first likelihood distribution calculating unit 102 . Specifically, the tracking availability determining unit 103 calculates the difficulty of tracking the first image 60 in each shooting direction based on the first likelihood distribution calculated by the first likelihood distribution calculating unit 102 do. Since the calculation method of the tracking difficulty is the same as that of the first embodiment, the description is omitted. Further, the tracking enable/disable determination unit 103 determines that tracking of the marker 62 is impossible when the tracking difficulty is higher than a predetermined threshold value. After that, the tracking enable/disable determination unit 103 outputs to the tracking unit 104 the determination result of the tracking of the marker 62 for each photographing direction. On the other hand, unlike the first embodiment, the tracking availability determination unit 103 does not output a determination result to the second image acquisition unit 105.

The second image acquisition unit 105 acquires a plurality of second images in different photographing directions as perspective images of the patient P generated at different times from the first image. For example, the second image is an image captured by the radiation detector 30 during treatment of patient P. Specifically, the second image acquisition unit 105 acquires both the perspective image captured by the radiation detector 30-1 and the perspective image captured by the radiation detector 30-2 as the second image. .

The second likelihood distribution calculation unit 106 calculates a second likelihood distribution representing a likelihood distribution in the second image acquired by the second image acquiring unit 105 . Specifically, the second likelihood distribution calculator 106 calculates the likelihood distribution in the perspective image (second image) captured by the radiation detector 30-1 and the image captured by the radiation detector 30-2. A likelihood distribution in the rendered perspective image (second image) is calculated as a second likelihood distribution. Here, the second likelihood distribution calculator 106 does not calculate the second likelihood distribution for the entire second image, but calculates the second likelihood distribution for the tracking area 61 in the second image. Since the calculation method of the second likelihood distribution is the same as the calculation method of the first likelihood distribution, description thereof is omitted.

The tracking unit 104 determines a tracking area 61 (FIG. 3), which is an area for tracking the position of the marker 62, based on the determination result of the tracking availability determining unit 103. Specifically, the tracking unit 104 sets the tracking area 61 to the second image in the shooting direction for which the tracking difficulty of the marker 62 is determined to be higher than a predetermined threshold value by the tracking availability determining unit 103. confined to the area on the polar line.

For example, it is assumed that the tracking difficulty in the imaging direction of the radiation detector 30-1 is higher than a predetermined threshold, and the tracking difficulty in the imaging direction of the radiation detector 30-2 is less than or equal to the predetermined threshold. In this case, when the position of the marker 62 is specified from the second image taken by the radiation detector 30-2, the position of the marker 62 in the second image taken by the radiation detector 30-1 is determined. The position is geometrically defined on the epipolar line. For this reason, the tracking unit 104 limits the tracking area 61 to the area on the epipolar line with respect to the second image captured by the radiation detector 30-1.

In this way, based on the tracking difficulty, a shooting direction in which the marker 62 is easy to track is determined, and from the second image in the shooting direction in which tracking is difficult, the tracking area 61 is limited to an area on the epipolar line, and the marker ( 62) to follow. In this way, the medical image processing apparatus 200 of the present embodiment can improve tracking accuracy of the marker 62 .

Fig. 8 is a flowchart showing the operation of the medical image processing apparatus in the previous stage of treating a patient according to the second embodiment. The process according to this flowchart is executed by the medical image processing apparatus 200 in a step prior to the treatment by irradiation of the treatment beam B on the patient P. In addition, since steps S301 to S303 in FIG. 8 are the same as steps S101 to S103 in FIG. 5 , descriptions are omitted.

The tracking availability determining unit 103 determines whether there is a tracking difficulty higher than a predetermined threshold among the tracking difficulties in each shooting direction calculated in step S303 (S304). If there is no tracking difficulty higher than the predetermined threshold (S304: No), the tracking unit 104 ends the processing according to the present flowchart without changing the tracking area 61. On the other hand, if there is a tracking difficulty higher than the predetermined threshold (S304: Yes), the tracking unit 104 determines the location of the marker 62 in the photographing direction with the lowest tracking difficulty and the highest tracking difficulty. A straight line connecting the imaging position in the lower imaging direction (the position of the radiation detector 30) is calculated as an epipolar line (S305). After that, the tracking unit 104 limits the tracking area 61 in the shooting direction where the tracking difficulty is higher than a predetermined threshold to the area on the epipolar line calculated in step S305 (S306), and the processing according to the present flowchart quit

In this way, the tracking unit 104 does not change the tracking area 61 for the second image in the shooting direction for which the tracking difficulty is determined to be equal to or less than a predetermined threshold. On the other hand, the tracking unit 104 assigns the tracking area 61 to the second image in the shooting direction in which the tracking difficulty is determined to be higher than a predetermined threshold, and sets the tracking area 61 to the marker 62 in the shooting direction with the lowest tracking difficulty. It is limited to the area on the epipolar line calculated based on the position. In this way, the medical image processing apparatus 200 of the present embodiment can improve tracking accuracy of the marker 62 .

(Third Embodiment)

In the first embodiment and the second embodiment, an irradiation control device 50 for controlling the treatment beam irradiation door 40 is provided. In contrast, in the third embodiment, it is assumed that the irradiation control device 50 is not provided in the treatment system 1, and the radiation treatment device 300 has a function of controlling the treatment beam irradiation door 40. . Hereinafter, the third embodiment will be described in detail.

9 is a block diagram showing a schematic configuration of a radiation treatment apparatus according to a third embodiment. In Fig. 9, the same reference numerals are assigned to parts corresponding to the respective parts in Fig. 2, and descriptions thereof are omitted. The radiation treatment apparatus 300 according to the third embodiment includes an irradiation control unit 301.

The tracking unit 104 determines the position of the marker 62 in the second image based on the second likelihood distribution calculated by the second likelihood distribution calculating unit 106 . For example, the tracking unit 104 determines that the position of the maximum value in the second likelihood distribution is the position of the marker 62 .

The tracking unit 104 determines the irradiation timing of the treatment beam B based on the determined position of the marker 62 . The positional relationship between the marker 62 and the lesion 63 can be specified from a fluoroscopic image of patient P obtained during treatment planning. For this reason, the tracking unit 104 instructs irradiation of the treatment beam B when the position of the lesion 63 in the body of the patient P, which is specified based on the position of the marker 62, is located within a predetermined range. An irradiation instruction signal is output to the irradiation controller 301 .

The irradiation control unit 301 irradiates the treatment beam B from the treatment beam irradiation door 40 according to the irradiation instruction signal output from the tracking unit 104 . In this way, the treatment beam B can be irradiated to the lesion 63 in the body of the patient P.

On the other hand, the tracking unit 104 transmits an irradiation instruction signal to the irradiation control unit 301 when the position of the lesion 63 in the body of patient P, which is specified based on the position of the marker 62, is not located within a predetermined range. ) is not output. In this way, irradiation of the treatment beam B to areas other than the lesion 63 can be suppressed.

10 is a flowchart showing the operation of the radiation treatment apparatus during treatment of a patient according to the third embodiment. The process according to this flowchart is repeatedly executed at predetermined time intervals by the radiation treatment apparatus 300 in the step of performing treatment by irradiation of the treatment beam B on the patient P. In addition, since steps S401 to S403 in FIG. 10 are the same as steps S201 to S203 in FIG. 6 , descriptions thereof are omitted.

The irradiation control unit 301 irradiates the treatment beam B from the treatment beam irradiation door 40 according to the position of the marker 62 (object) determined by the tracking unit 104 in step S403. For example, the irradiation control unit 301 controls the treatment beam irradiation door 40 when the position of the lesion 63 in the body of the patient P, which is specified based on the position of the marker 62, is located within a predetermined range. The treatment beam B is irradiated from

In this way, in the radiation treatment apparatus 300 according to the third embodiment, in addition to the functions of the medical image processing apparatus 100 according to the first embodiment, the radiation control unit 301 controls the treatment beam irradiation door 40. ) is provided. Also with the radiation treatment apparatus 300 of the present embodiment, the tracking accuracy of the marker 62 can be improved as in the first embodiment.

In the above embodiment, the object tracked by the tracking unit 104 is a metal marker placed inside the patient P's body, but it may be a lesion inside the patient P's body. In this case, an image including the entire lesion or a part of the lesion may be cut out from the first image and used as a template image. In the case of a DRR image generated from a CT image in which the first image includes treatment planning information, since the position of a lesion in the CT image is included in the treatment planning information, the image onto which this lesion is projected may be used as a template image. . In the case where the first image is an X-ray fluoroscopy image captured by the radiation detector 30 in determining the position of the patient P, since the DRR image and the position of the patient P coincide, the location of the lesion is diverted, An X-ray perspective image of , may be cut out and used as a template image.

Further, the tracking availability determination unit 103 may present the tracking difficulty in each shooting direction to the user using a notification unit (not shown). For example, the tracking enable/disable determination unit 103 may notify a shooting direction with a low tracking difficulty when the user plans a shooting direction. In this way, the user can estimate the success rate of the breathing synchronization survey method and determine whether tracking of the marker 62 may be limited to only the second image in one shooting direction.

In addition, the above-described medical image processing apparatuses 100 and 200 and the radiation treatment apparatus 300 can be realized by using, for example, a general-purpose computer device as basic hardware. That is, the first image acquisition unit 101, the first likelihood distribution calculation unit 102, the tracking enable decision unit 103, the tracking unit 104, the second image acquisition unit 105, the second likelihood distribution calculation unit (106) and the irradiation control unit 301 can be realized by executing a program in the processor installed in the computer device described above. At this time, the medical image processing apparatuses 100 and 200 and the radiation treatment apparatus 300 may be realized by installing the above programs in advance in a computer device, storing them in a storage medium such as a CD-ROM, or via a network. It may be realized by distributing the above program and properly installing this program in a computer device. In addition, B and C can be realized by appropriately using a storage medium such as a built-in or external memory, a hard disk, or a CD-R, CD-RW, DVD-RAM, or DVD-R in the above computer device.

Although several embodiments of the present invention have been described so far, these embodiments are presented as examples and are not intended to limit the scope of the invention. Such a novel embodiment can be implemented in various other forms, and various omissions, substitutions, and changes can be made within a range not departing from the gist of the invention. While being included in the scope and gist of the invention, these embodiments and variations thereof are included in the scope of the invention described in the claims and their equivalents.

1: treatment system
100: medical image processing device
101: first image acquisition unit
102: first likelihood distribution calculator
103: tracking availability determination unit
104: tracking unit
105: second image acquisition unit
106: second likelihood distribution calculator
200: medical image processing device
300: radiation therapy device
301: investigation control unit

Claims (11)

A medical image processing device for tracking the position of an object in a patient's body,
a first image acquisition unit that acquires a plurality of first images of different photographing directions as fluoroscopic images of the patient;
a second image acquisition unit that acquires a plurality of second images of different photographing directions as perspective images of the patient generated at different times from the first image;
a first likelihood distribution calculation unit that calculates a first likelihood distribution indicating a distribution of likelihoods representing features of the object in each of the plurality of first images acquired by the first image acquisition unit;
a tracking availability determining unit for determining whether or not tracking of the object is possible based on the first likelihood distribution calculated by the first likelihood distribution calculating unit;
and a tracking unit for tracking a position of the object in the second image acquired by the second image acquisition unit according to a result of the determination of the tracking availability determination unit. According to claim 1,
The medical image processing apparatus according to claim 1 , wherein the second image acquisition unit determines a photographing direction of the second image based on a determination result of the tracking enable/disable determination unit. According to claim 2,
The medical image processing apparatus of claim 1 , wherein the second image acquiring unit determines a photographing direction of the second image used for tracking the position of the object by the tracking unit before treatment is performed on the patient. According to claim 1,
a second likelihood distribution calculation unit that calculates a second likelihood distribution representing the likelihood distribution in the second image;
The medical image processing apparatus of claim 1 , wherein the tracking unit determines a position of the object in the second image based on the second likelihood distribution calculated by the second likelihood distribution calculating unit. According to claim 1,
The medical image processing apparatus of claim 1 , wherein the tracking unit determines a tracking area, which is an area in which the location of the object is tracked, based on a result of the determination of the tracking enable/disable decision unit. According to claim 5,
The tracking availability determining unit calculates a tracking difficulty indicating a difficulty of tracking the object in the second image;
The medical image processing apparatus of claim 1 , wherein the tracking unit limits the tracking area to an area on an epipolar line for the second image in which the tracking difficulty calculated by the tracking availability determining unit is higher than a predetermined threshold. According to any one of claims 1 to 6,
The medical image processing apparatus, wherein the object is a metal marker. According to any one of claims 1 to 7,
The first image is a perspective image generated based on a three-dimensional image of the patient taken during treatment planning, or a perspective image taken from the same shooting direction as the second image immediately before treatment,
The second image is a perspective image captured during treatment of the patient. A medical image processing method for tracking the position of an object in a patient's body,
a first image acquisition step of acquiring a plurality of first images of different photographing directions as perspective images of the patient;
a second image acquisition step of acquiring a plurality of second images of different photographing directions as perspective images of the patient generated at different times from the first image;
a first likelihood distribution calculation step of calculating a first likelihood distribution representing a distribution of likelihoods representing characteristics of the object in each of the plurality of first images acquired by the first image acquisition step;
a tracking availability decision step of determining whether tracking of the object is possible based on the first likelihood distribution calculated by the first likelihood distribution calculation step;
and a tracking step of tracking a position of the object in the second image acquired by the second image acquiring step according to a determination result of the tracking enable/disable judgment step. A medical image processing program for tracking the position of an object in a patient's body,
on the computer,
a first image acquisition step of acquiring a plurality of first images of different photographing directions as perspective images of the patient;
a second image acquisition step of acquiring a plurality of second images of different photographing directions as perspective images of the patient generated at different times from the first image;
a first likelihood distribution calculation step of calculating a first likelihood distribution representing a distribution of likelihoods representing characteristics of the object in each of the plurality of first images acquired by the first image acquisition step;
a tracking availability decision step of determining whether tracking of the object is possible based on the first likelihood distribution calculated by the first likelihood distribution calculation step;
The medical image processing program that executes a tracking process for tracking a position of the object in the second image acquired by the second image acquisition process according to a determination result of the tracking enable/disable judgment process. A radiation therapy apparatus for irradiating radiation to the patient while tracking the position of an object in the patient's body,
a first image acquisition unit that acquires a plurality of first images of different photographing directions as fluoroscopic images of the patient;
a second image acquisition unit that acquires a plurality of second images of different photographing directions as perspective images of the patient generated at different times from the first image;
a first likelihood distribution calculation unit that calculates a first likelihood distribution indicating a distribution of likelihoods representing features of the object in each of the plurality of first images acquired by the first image acquisition unit;
a tracking availability determining unit for determining whether or not tracking of the object is possible based on the first likelihood distribution calculated by the first likelihood distribution calculating unit;
a tracking unit that tracks the position of the object in the second image acquired by the second image acquisition unit according to a result of determination of the tracking enable/disable determination unit;
A radiation treatment apparatus comprising an irradiation control unit for controlling irradiation of the radiation according to the position of the object tracked by the tracking unit.

Images